The American journal of emergency medicine
-
Identifying patients at imminent risk of death is a paramount priority in combat casualty care. This study measures the vital sign values predictive of mortality among combat casualties in Iraq and Afghanistan. ⋯ Casualties with a systolic blood pressure <112 mmHg, are at high risk of mortality, a value significantly higher than the traditional 90 mmHg threshold. Our dataset highlights the need for better methods to guide resuscitation as vital sign measurements have limited accuracy in predicting mortality.
-
Management of patients with syncope lacks standardization. We sought to assess regional variation in hospitalization rates and resource utilization of patients with syncope. ⋯ Significant regional variability in hospitalization rates and ED service charges exist among patients with syncope. Standardizing practices may be needed to reduce variability.
-
Multicenter Study Comparative Study Observational Study
Comparison of 4 tests' utility for predicting need for emergency department care in patients with alcohol-related complaints.
Intoxication is a common presenting complaint in emergency departments (ED), but many patients with intoxication do not need emergency care. Three screens (BLINDED, Brown, and San Francisco) attempt to determine which intoxicated patients can be triaged to a lower level of care. ⋯ The three formal screens and provider gestalt performed similarly.
-
Multicenter Study
Serum total carbon dioxide as a prognostic factor for 28-day mortality in patients with sepsis.
Metabolic acidosis is commonly associated with the disease severity in patients with sepsis or septic shock. This study was performed to investigate the association between serum total carbon dioxide (TCO2) concentration and 28-day mortality in patients with sepsis. ⋯ Serum TCO2 concentrations of 20 mmol/l or less were associated with 28-day mortality in patients with sepsis.
-
Comparative Study
Comparison of MPL-ANN and PLS-DA models for predicting the severity of patients with acute pancreatitis: An exploratory study.
Acute pancreatitis (AP) is a common inflammatory disorder that may develop into severe AP (SAP), resulting in life-threatening complications and even death. The purpose of this study was to explore two different machine learning models of multilayer perception-artificial neural network (MPL-ANN) and partial least squares-discrimination (PLS-DA) to diagnose and predict AP patients' severity. ⋯ The results demonstrated that the MPL-ANN model based on routine blood and serum biochemical indexes provides a reliable and straightforward daily clinical practice tool to predict AP patients' severity.